Vicuna¶

latest33b13b7b33b-q4_033b-q4_133b-q5_033b-q5_133b-q8_033b-q2_K33b-q3_K_S33b-q3_K_M33b-q3_K_L33b-q4_K_S33b-q4_K_M33b-q5_K_S33b-q5_K_M33b-q6_K33b-fp1613b-16k13b-q4_013b-q4_113b-q5_013b-q5_113b-q8_013b-q2_K13b-q3_K_S13b-q3_K_M13b-q3_K_L13b-q4_K_S13b-q4_K_M13b-q5_K_S13b-q5_K_M13b-q6_K13b-fp1613b-v1.5-q4_013b-v1.5-q4_113b-v1.5-q5_013b-v1.5-q5_113b-v1.5-q8_013b-v1.5-q2_K13b-v1.5-q3_K_S13b-v1.5-q3_K_M13b-v1.5-q3_K_L13b-v1.5-q4_K_S13b-v1.5-q4_K_M13b-v1.5-q5_K_S13b-v1.5-q5_K_M13b-v1.5-q6_K13b-v1.5-fp1613b-v1.5-16k-q4_013b-v1.5-16k-q4_113b-v1.5-16k-q5_013b-v1.5-16k-q5_113b-v1.5-16k-q8_013b-v1.5-16k-q2_K13b-v1.5-16k-q3_K_S13b-v1.5-16k-q3_K_M13b-v1.5-16k-q3_K_L13b-v1.5-16k-q4_K_S13b-v1.5-16k-q4_K_M13b-v1.5-16k-q5_K_S13b-v1.5-16k-q5_K_M13b-v1.5-16k-q6_K13b-v1.5-16k-fp167b-16k7b-q4_07b-q4_17b-q5_07b-q5_17b-q8_07b-q2_K7b-q3_K_S7b-q3_K_M7b-q3_K_L7b-q4_K_S7b-q4_K_M7b-q5_K_S7b-q5_K_M7b-q6_K7b-fp167b-v1.5-q4_07b-v1.5-q4_17b-v1.5-q5_07b-v1.5-q5_17b-v1.5-q8_07b-v1.5-q2_K7b-v1.5-q3_K_S7b-v1.5-q3_K_M7b-v1.5-q3_K_L7b-v1.5-q4_K_S7b-v1.5-q4_K_M7b-v1.5-q5_K_S7b-v1.5-q5_K_M7b-v1.5-q6_K7b-v1.5-fp167b-v1.5-16k-q4_07b-v1.5-16k-q4_17b-v1.5-16k-q5_07b-v1.5-16k-q5_17b-v1.5-16k-q8_07b-v1.5-16k-q2_K7b-v1.5-16k-q3_K_S7b-v1.5-16k-q3_K_M7b-v1.5-16k-q3_K_L7b-v1.5-16k-q4_K_S7b-v1.5-16k-q4_K_M7b-v1.5-16k-q5_K_S7b-v1.5-16k-q5_K_M7b-v1.5-16k-q6_K7b-v1.5-16k-fp16

拉取模型
```
ollama run vicuna
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	370739dc897b · 3.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 4-bit	86f0704901a4 · 18GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	e311d03837d9 · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	370739dc897b · 3.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 4-bit	86f0704901a4 · 18GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 4-bit	4b40d8826503 · 20GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 5-bit	4a6fa67158d8 · 22GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 5-bit	732296977ff9 · 24GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 8-bit	dc6380cf87ce · 35GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 2-bit	9129a0b1a6b1 · 14GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 3-bit	029c30fb56ac · 14GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 3-bit	fe6ff250b94e · 16GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 3-bit	5f73c820980e · 17GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 4-bit	933cc774ba3c · 18GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 4-bit	ae8f63e7638e · 20GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 5-bit	87a62b85e56f · 22GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 5-bit	45a15331c3d3 · 23GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization 6-bit	594c8ae461ac · 27GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:33b-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 30B quantization F16	6bc47b18a625 · 65GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-16k
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	4ea0e2b82bc2 · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	a6aad17d1205 · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	d7b312e7d741 · 8.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	d775a7c5294b · 9.0GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	65711d83a5ba · 9.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 8-bit	1f4a6e7b304c · 14GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 2-bit	c243d669ad2e · 5.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	a1f4ecdb04ba · 5.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	5c94116bb4df · 6.3GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	3ce284b06308 · 6.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	96cc0c85539e · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	0f5697218aef · 7.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	9151c66c59cf · 9.0GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	57fc4dcc89d7 · 9.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 6-bit	5771033f82b8 · 11GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization F16	5c0aaca02f10 · 26GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	e311d03837d9 · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	ca8047f969be · 8.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	33be3d9112bd · 9.0GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	b03c2008cb04 · 9.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 8-bit	db82e78d570a · 14GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 2-bit	da124fb49a03 · 5.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	db9d5d8832a5 · 5.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	112a0a219973 · 6.3GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	3a1c75a39e39 · 6.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	c78c1ae11f55 · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	d81bdd5ae575 · 7.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	d3dd8af1f363 · 9.0GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	c85a3d3b3b78 · 9.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 6-bit	90d7ed92be1d · 11GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization F16	3e2035c21594 · 26GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	4ea0e2b82bc2 · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	beaca53a59b9 · 8.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	8994818e295d · 9.0GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	b1e60bd134ff · 9.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 8-bit	7e91afb2b027 · 14GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 2-bit	c4bc2aac929f · 5.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	460254d8fc30 · 5.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	f713797047ce · 6.3GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 3-bit	2354833bf609 · 6.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	6c1dcf76ddbd · 7.4GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 4-bit	99611d39169d · 7.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	5d960ceab7d0 · 9.0GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 5-bit	3374b3e9b520 · 9.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization 6-bit	3dabce096571 · 11GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:13b-v1.5-16k-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 13B quantization F16	aa225f209212 · 26GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-16k
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	e17473565403 · 3.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	722cb0fe032d · 3.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	daba6226e41c · 4.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	b4be80922f5c · 4.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	3958ed7d2994 · 5.1GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 8-bit	abbdf2e7dab4 · 7.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 2-bit	7b111124e218 · 2.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	2b471de7ac09 · 2.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	a510caa0fb6b · 3.3GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	1ac57ff324d2 · 3.6GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	7b22215a6f5a · 3.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	e702c3f6d1da · 4.1GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	aa085ae496ef · 4.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	2cc1a91b3ee5 · 4.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 6-bit	5bbfe6ccf426 · 5.5GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization F16	2b09615317cc · 13GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	154B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	370739dc897b · 3.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	49882f87f7a7 · 4.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	48de3e58864e · 4.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	fa2d15c41d43 · 5.1GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 8-bit	df07a6d74df1 · 7.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 2-bit	ce1d7d2d4c36 · 2.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	d4a35f8b2ff8 · 2.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	b617de3e65a1 · 3.3GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	5958c72021fe · 3.6GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	9dbfd37d1be3 · 3.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	33b5fd751101 · 4.1GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	6167e172bf05 · 4.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	f734686befb8 · 4.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 6-bit	cfceb01fd96f · 5.5GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization F16	1e2de112296e · 13GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"stop":["USER:","ASSISTANT:"]}`	31B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q4_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	e17473565403 · 3.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q4_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	8af11c99918c · 4.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q5_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	5c89be046446 · 4.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q5_1
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	8988900a59a5 · 5.1GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q8_0
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 8-bit	32abbaf4d985 · 7.2GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q2_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 2-bit	409c84f8f2cb · 2.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q3_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	e82ccebcca5c · 2.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q3_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	9cd3422a7f75 · 3.3GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q3_K_L
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 3-bit	6e9eee2fdf07 · 3.6GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q4_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	cc8bb49d8400 · 3.9GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q4_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 4-bit	493df7220cb7 · 4.1GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q5_K_S
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	52cf0588ba15 · 4.7GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q5_K_M
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 5-bit	20d16dc9be3e · 4.8GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-q6_K
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization 6-bit	62fe512efb47 · 5.5GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B

拉取模型
```
ollama run vicuna:7b-v1.5-16k-fp16
```

模型信息 (model)

Manifest	Info	Size
model	arch llama parameters 7B quantization F16	7a1b09b09a43 · 13GB
system	`A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.`	155B
template	`{{ .System }} USER: {{ .Prompt }} ASSISTANT:`	45B
params	`{"num_ctx":16384,"rope_frequency_scale":0.125,"stop":["USER:","ASSISTANT:"]}`	76B